Face¶
Face Detection¶
DenseBox (2015)¶
MTCNN (SPL 2016)¶
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
code: https://kpzhang93.github.io/MTCNN_face_detection_alignment/
Detection & landmark
Pyramid
PNet, RNet ONet
SSH (ICCV 2017)¶
SSH: Single Stage Headless Face Detector
decrease inference time
scale-invariant
fixed size arcter to replace proposal
DSFD (CVPR 2019)¶
DSFD: Dual Shot Face Detector
Feature Enhance Module (FEM)
Face Feature Embedding¶
Could used for recognition with simple classifier
DDML (CVPR 2014)¶
Discriminative Deep Metric Learning for Face Verification in the Wild learn a nonlinear transformations and yield discriminative deep metric with a margin between positive and negative image pairs
Contrastive Loss¶
Same class => close
Different class => distance > margin m
FaceNet (CVPR 2015)¶
FaceNet: A Unified Embedding for Face Recognition and Clustering
Triplet Loss¶
inspirated by LMNN (large margin nearest neighbor)
Triplet Loss with VAE
Triplet selection/ present a novel online negative exemplar mining strategy which ensures consistently increasing difficulty of triplets as the network trains
disadv: data expansion when constituting the sample pairs
Centre Loss (ECCV 2016)¶
A Discriminative Feature Learning Approach for Deep Face Recognition add center Loss to softmax, hence the model discriminative power enhanced
SphereFace (CVPR 2017)¶
SphereFace: Deep Hypersphere Embedding for Face Recognition
in an angular space and penalises the angles between deep features
normalize W, optimize feature embedding and angle
disadv: requires a series of approximation in order to be computed,, resulted in unstable training. softmax loss used to stabilise training dominate the training process.
CosFace (CVPR 2018)¶
add cosine margin penalty to the target logit admits easier implementation and relieves the need for joint supervision from the softmax loss
ArcFace¶
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
MXNet: InsightNet RetinaNet: detection, InsightNet: embedding